uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
GPU: Power vs Performance
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology.
2014 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

GPUs are widely being used to meet the ever increasing demands of High performance computing. High-end GPUs are one of the highest consumers of power in a computer. Power dissipation has always been a major concern area  for computer architects.  Due to power efficiency demands modern CPUs have moved towards multicore architectures. GPUs are already massively parallel architectures. There has been some encouraging results for power efficiency in CPUs by applying DVFS . The vision is that a similar approach would also provide encouraging results for power efficiency in GPUs.

In this thesis we have analyzed the power and performance characteristics of GPU at different frequencies. To help us achieve that, we have made a set of  microbenchmarks with different levels of memory boundedness and threads. We have also used benchmarks from CUDA SDK and Parboil. We have used a GTX580 Fermi based GPU. We have also made a hardware infrastructure that accurately measures the power being consumed by the GPU.

Place, publisher, year, edition, pages
IT, 14 015
National Category
Engineering and Technology
URN: urn:nbn:se:uu:diva-237364OAI: oai:DiVA.org:uu-237364DiVA: diva2:767619
Educational program
Master Programme in Computer Science
Available from: 2014-12-02 Created: 2014-12-02 Last updated: 2014-12-02Bibliographically approved

Open Access in DiVA

fulltext(3008 kB)313 downloads
File information
File name FULLTEXT01.pdfFile size 3008 kBChecksum SHA-512
Type fulltextMimetype application/pdf

By organisation
Department of Information Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 313 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 5461 hits
ReferencesLink to record
Permanent link

Direct link